Security audit
Kandinsky
Security checks across malware telemetry and agentic risk
Overview
This skill coherently generates and edits media through a user-configured Kandinsky API and does not show hidden or unrelated behavior.
Install only if you trust the configured Kandinsky API instance, because prompts and any input images or audio you choose will be sent there with your API key. Keep the key private, prefer HTTPS or private/loopback API addresses, and use insecure transport or censor-disabling options only deliberately.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.